Paper Citation Record · LEDGER

Locate-Then-Examine: Grounded Region Reasoning Improves Detection of AI-Generated Images

As of 22 July 2026, this Paper Citation Record lists 30 of 30 outbound references and 3 inbound Pith citation observations for arXiv:2510.04225.

A citation records a reference. It does not transfer a finding from one paper to another.

pith.paper-citation-record.v1
2510.04225 v2

Coverage vector

measured 30 of 30 reference resolution

Typed states for the displayed outbound observations.

Source: paper_references, paper_reference_links, observed 2026-05-18T10:13:08.112072Z

measured 33 of 33 standing notices

One-hop event checks from named stored sources.

Source: scholarly_work_events, retraction_status_cache, observed 2026-07-21T06:31:05.380196+00:00

measured 3 of 3 inbound itemization

Pith citing papers itemized under the disclosed page cap.

Source: paper_references, paper_reference_links, observed 2026-07-12T01:35:43.979206Z

measured 0 of 1 external citation measurements

A source-named dated measurement, never combined with another source.

Source: pith, observed 2026-05-15T05:29:46.630027Z

Reference resolution

30 of 30 outbound references displayed

verified exact14
verified fuzzy5
unresolved0
parse uncertain0
malformed identifier1
metadata mismatch10

External citation measurements

No source-named external measurement is stored.

Outbound references

Observation ff152506-aad0-419b-951e-0203fa02b2f5 · outbound

This paper cites Bleuberi: Bleu is a surprisingly effective reward for instruction following.arXiv preprint arXiv:2505.11080.

Locate-Then-Examine: Grounded Region Reasoning Improves Detection of AI-Generated Images Bleuberi: Bleu is a surprisingly effective reward for instruction following.arXiv preprint arXiv:2505.11080

Reference 1

Resolution: verified exact; arxiv_id, observed 2026-05-18T10:16:14.383452Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-07-21T06:31:05.380196+00:00.

Observation 043b4f5a-8eb2-43b1-900f-ba054de18900 · outbound

This paper cites AntifakePrompt: Prompt-Tuned Vision-Language Models are Fake Image Detectors.

Locate-Then-Examine: Grounded Region Reasoning Improves Detection of AI-Generated Images AntifakePrompt: Prompt-Tuned Vision-Language Models are Fake Image Detectors

Reference 2

Resolution: verified exact; arxiv_id, observed 2026-05-18T10:16:14.366948Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-07-21T06:31:05.380196+00:00.

Observation ce35e764-dc80-440c-9624-75d245551088 · outbound

This paper cites Microsoft COCO Captions: Data Collection and Evaluation Server.

Locate-Then-Examine: Grounded Region Reasoning Improves Detection of AI-Generated Images Microsoft COCO Captions: Data Collection and Evaluation Server

Reference 3

Resolution: verified exact; local_arxiv, observed 2026-05-18T10:16:14.416463Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-07-21T06:31:05.380196+00:00.

Observation 615431af-7f0e-431a-bdaf-3d8672946a2a · outbound

This paper cites Visual thoughts: A unified perspective of understanding multimodal chain-of-thought.arXiv preprint arXiv:2505.15510.

Locate-Then-Examine: Grounded Region Reasoning Improves Detection of AI-Generated Images Visual thoughts: A unified perspective of understanding multimodal chain-of-thought.arXiv preprint arXiv:2505.15510

Reference 4

Resolution: verified exact; arxiv_id, observed 2026-05-18T10:16:14.400220Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-07-21T06:31:05.380196+00:00.

Observation 01882f35-04f6-46e6-b4bc-6522294463c5 · outbound

This paper cites In: ICASSP 2023 - 2023 IEEE Inter- national Conference on Acoustics, Speech and Signal Processing (ICASSP), pp.

Locate-Then-Examine: Grounded Region Reasoning Improves Detection of AI-Generated Images In: ICASSP 2023 - 2023 IEEE Inter- national Conference on Acoustics, Speech and Signal Processing (ICASSP), pp

Reference 5

Resolution: verified exact; arxiv_id, observed 2026-05-18T10:16:13.633151Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-07-21T06:31:05.380196+00:00.

Observation 8b981fc6-76b5-4a4c-a00b-8a8519489161 · outbound

This paper cites GRIT: Teaching MLLMs to Think with Images.

Locate-Then-Examine: Grounded Region Reasoning Improves Detection of AI-Generated Images GRIT: Teaching MLLMs to Think with Images

Reference 6

Resolution: metadata mismatch; local_arxiv, observed 2026-05-18T10:16:14.380167Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-07-21T06:31:05.380196+00:00.

Observation 2ff604da-1fc2-4ddb-af5c-2fd33c55a1e0 · outbound

This paper cites ISBN 9781450362016.

Locate-Then-Examine: Grounded Region Reasoning Improves Detection of AI-Generated Images ISBN 9781450362016

Reference 7

Resolution: verified exact; arxiv_id, observed 2026-05-18T10:16:13.641269Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-07-21T06:31:05.380196+00:00.

Observation f6fcca5d-1b13-4a95-b120-fe8b624444c8 · outbound

This paper cites Denoising Diffusion Probabilistic Models.

Locate-Then-Examine: Grounded Region Reasoning Improves Detection of AI-Generated Images Denoising Diffusion Probabilistic Models

Reference 8

Resolution: verified exact; local_arxiv, observed 2026-05-18T10:16:14.377241Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-07-21T06:31:05.380196+00:00.

Observation b76647d9-ca84-47eb-92a3-b08446324d25 · outbound

This paper cites Vision-R1: Incentivizing Reasoning Capability in Multimodal Large Language Models.

Locate-Then-Examine: Grounded Region Reasoning Improves Detection of AI-Generated Images Vision-R1: Incentivizing Reasoning Capability in Multimodal Large Language Models

Reference 9

Resolution: metadata mismatch; local_arxiv, observed 2026-05-18T10:16:14.363289Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-07-21T06:31:05.380196+00:00.

Observation 4537cc8c-aeb7-4f2e-a712-b6ef60cde649 · outbound

This paper cites Hengrui Kang, Siwei Wen, Zichen Wen, Junyan Ye, Weijia Li, Peilin Feng, Baichuan Zhou, Bin Wang, Dahua Lin, Linfeng Zhang, et al.

Locate-Then-Examine: Grounded Region Reasoning Improves Detection of AI-Generated Images Hengrui Kang, Siwei Wen, Zichen Wen, Junyan Ye, Weijia Li, Peilin Feng, Baichuan Zhou, Bin Wang, Dahua Lin, Linfeng Zhang, et al

Reference 10

Resolution: verified exact; arxiv_id, observed 2026-05-18T10:16:14.360158Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-07-21T06:31:05.380196+00:00.

Observation 45ff3ac9-20ca-4966-b64f-d54c27368c1f · outbound

This paper cites RewardBench: Evaluating Reward Models for Language Modeling.

Locate-Then-Examine: Grounded Region Reasoning Improves Detection of AI-Generated Images RewardBench: Evaluating Reward Models for Language Modeling

Reference 11

Resolution: metadata mismatch; arxiv_id, observed 2026-05-18T10:16:14.370848Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-07-21T06:31:05.380196+00:00.

Observation 11964371-3d37-4a97-9046-f5a3b87c5fde · outbound

This paper cites FakeBench: Probing Explainable Fake Image Detection via Large Multimodal Models.

Locate-Then-Examine: Grounded Region Reasoning Improves Detection of AI-Generated Images FakeBench: Probing Explainable Fake Image Detection via Large Multimodal Models

Reference 12

Resolution: verified exact; arxiv_id, observed 2026-05-18T10:16:14.426884Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-07-21T06:31:05.380196+00:00.

Observation 13565f91-7f65-42aa-a1e7-b5cfd6810db5 · outbound

This paper cites Chin-Yew Lin.

Locate-Then-Examine: Grounded Region Reasoning Improves Detection of AI-Generated Images Chin-Yew Lin

Reference 13

Resolution: verified exact; arxiv_id, observed 2026-05-18T10:16:13.637415Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-07-21T06:31:05.380196+00:00.

Observation 61857e1c-7081-479a-a066-a429f9b75eb3 · outbound

This paper cites MedVLM-R1: Incentivizing Medical Reasoning Capability of Vision-Language Models (VLMs) via Reinforcement Learning.

Locate-Then-Examine: Grounded Region Reasoning Improves Detection of AI-Generated Images MedVLM-R1: Incentivizing Medical Reasoning Capability of Vision-Language Models (VLMs) via Reinforcement Learning

Reference 14

Resolution: metadata mismatch; arxiv_id, observed 2026-05-18T10:16:14.423376Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-07-21T06:31:05.380196+00:00.

Observation 02fc4e04-ac53-4e01-b2d1-0e7b0f6bee19 · outbound

This paper cites Community Forensics: Using Thousands of Generators to Train Fake Image Detectors.

Locate-Then-Examine: Grounded Region Reasoning Improves Detection of AI-Generated Images Community Forensics: Using Thousands of Generators to Train Fake Image Detectors

Reference 15

Resolution: verified exact; arxiv_id, observed 2026-05-18T10:16:14.419454Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-07-21T06:31:05.380196+00:00.

Observation 0129da27-4500-4ffb-b80c-8117cd133e24 · outbound

This paper cites Jonas Ricker, Denis Lukovnikov, and Asja Fischer.

Locate-Then-Examine: Grounded Region Reasoning Improves Detection of AI-Generated Images Jonas Ricker, Denis Lukovnikov, and Asja Fischer

Reference 16

Resolution: verified fuzzy; raw_fallback, observed 2026-05-18T10:16:14.833458Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-07-21T06:31:05.380196+00:00.

Observation bf1f8fba-1636-43bc-ae41-3981090d4ba4 · outbound

This paper cites DeepSeekMath: Pushing the Limits of Mathematical Reasoning in Open Language Models.

Locate-Then-Examine: Grounded Region Reasoning Improves Detection of AI-Generated Images DeepSeekMath: Pushing the Limits of Mathematical Reasoning in Open Language Models

Reference 17

Resolution: metadata mismatch; local_arxiv, observed 2026-05-18T10:16:14.374299Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-07-21T06:31:05.380196+00:00.

Observation fff33ceb-3f67-463e-8fb9-bccd012610cf · outbound

This paper cites Satori-r1: Incentivizing multimodal reasoning through explicit visual anchoring.

Locate-Then-Examine: Grounded Region Reasoning Improves Detection of AI-Generated Images Satori-r1: Incentivizing multimodal reasoning through explicit visual anchoring

Reference 18

Resolution: metadata mismatch; arxiv_id, observed 2026-05-18T10:16:14.413309Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-07-21T06:31:05.380196+00:00.

Observation c87f48e4-c843-4aa0-b84a-a083a0152579 · outbound

This paper cites Denoising Diffusion Implicit Models.

Locate-Then-Examine: Grounded Region Reasoning Improves Detection of AI-Generated Images Denoising Diffusion Implicit Models

Reference 19

Resolution: verified exact; local_arxiv, observed 2026-05-18T10:16:14.410203Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-07-21T06:31:05.380196+00:00.

Observation 2028fe8f-4042-47b2-8846-0383e4a430e8 · outbound

This paper cites OpenThinkIMG: Learning to Think with Images via Visual Tool Reinforcement Learning.

Locate-Then-Examine: Grounded Region Reasoning Improves Detection of AI-Generated Images OpenThinkIMG: Learning to Think with Images via Visual Tool Reinforcement Learning

Reference 20

Resolution: metadata mismatch; local_arxiv, observed 2026-05-18T10:16:14.407108Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-07-21T06:31:05.380196+00:00.

Observation 7d6b5fe3-a256-490b-932a-5c6bcf8b2f76 · outbound

This paper cites VL-Rethinker: Incentivizing Self-Reflection of Vision-Language Models with Reinforcement Learning.

Locate-Then-Examine: Grounded Region Reasoning Improves Detection of AI-Generated Images VL-Rethinker: Incentivizing Self-Reflection of Vision-Language Models with Reinforcement Learning

Reference 21

Resolution: verified exact; local_arxiv, observed 2026-05-18T10:16:14.403423Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-07-21T06:31:05.380196+00:00.

Observation 59ee0f4e-8e78-40bf-9884-17d6dddf6adb · outbound

This paper cites Grounded Chain-of-Thought for Multimodal Large Language Models.

Locate-Then-Examine: Grounded Region Reasoning Improves Detection of AI-Generated Images Grounded Chain-of-Thought for Multimodal Large Language Models

Reference 22

Resolution: metadata mismatch; arxiv_id, observed 2026-05-18T10:16:14.393486Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-07-21T06:31:05.380196+00:00.

Observation e66e89f4-d440-4e3e-b524-5e817001d8cf · outbound

This paper cites FakeShield: Explainable Image Forgery Detection and Localization via Multi-modal Large Language Models.

Locate-Then-Examine: Grounded Region Reasoning Improves Detection of AI-Generated Images FakeShield: Explainable Image Forgery Detection and Localization via Multi-modal Large Language Models

Reference 23

Resolution: verified exact; arxiv_id, observed 2026-05-18T10:16:14.396809Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-07-21T06:31:05.380196+00:00.

Observation 20234973-0379-48a6-b2d3-9cf698023c68 · outbound

This paper cites R1-Onevision: Advancing Generalized Multimodal Reasoning through Cross-Modal Formalization.

Locate-Then-Examine: Grounded Region Reasoning Improves Detection of AI-Generated Images R1-Onevision: Advancing Generalized Multimodal Reasoning through Cross-Modal Formalization

Reference 24

Resolution: metadata mismatch; local_arxiv, observed 2026-05-18T10:16:14.389875Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-07-21T06:31:05.380196+00:00.

Observation e3b2f9b9-220c-4d33-b888-26d141eb5484 · outbound

This paper cites A-Bench: Are LMMs Masters at Evaluating AI-generated Images?.

Locate-Then-Examine: Grounded Region Reasoning Improves Detection of AI-Generated Images A-Bench: Are LMMs Masters at Evaluating AI-generated Images?

Reference 25

Resolution: metadata mismatch; arxiv_id, observed 2026-05-18T10:16:14.386638Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-07-21T06:31:05.380196+00:00.

Observation 60e2dc90-d351-47d3-8f12-7bcf91d1b31d · outbound

This paper cites These datasets provide diverse natural images spanning various object categories, ensuring broad coverage of real-world visual content.

Locate-Then-Examine: Grounded Region Reasoning Improves Detection of AI-Generated Images These datasets provide diverse natural images spanning various object categories, ensuring broad coverage of real-world visual content

Reference 26

Resolution: verified fuzzy; raw_fallback, observed 2026-05-18T10:16:14.842060Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-07-21T06:31:05.380196+00:00.

Observation d1610d65-01f6-4f1c-9243-fce03d59ae83 · outbound

This paper cites We found that at least 600 GB of VRAM is required to perform GRPO.

Locate-Then-Examine: Grounded Region Reasoning Improves Detection of AI-Generated Images We found that at least 600 GB of VRAM is required to perform GRPO

Reference 27

Resolution: verified fuzzy; raw_fallback, observed 2026-05-18T10:16:14.831401Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-07-21T06:31:05.380196+00:00.

Observation c4b3bd7a-df4c-4cc3-bba1-9b0333332628 · outbound

This paper cites Collectively, these methods represent diverse strategies from artifact analysis to semantic reasoning, advanc- ing the state of synthetic content detection.

Locate-Then-Examine: Grounded Region Reasoning Improves Detection of AI-Generated Images Collectively, these methods represent diverse strategies from artifact analysis to semantic reasoning, advanc- ing the state of synthetic content detection

Reference 28

Resolution: verified fuzzy; raw_fallback, observed 2026-05-18T10:16:14.839849Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-07-21T06:31:05.380196+00:00.

Observation 52dc3e5f-78c7-4ea1-bdeb-a42fe555d6ba · outbound

This paper cites an unresolved cited work.

Locate-Then-Examine: Grounded Region Reasoning Improves Detection of AI-Generated Images Unresolved cited work

Reference 29

Resolution: malformed identifier; raw_fallback, observed 2026-05-18T10:16:14.837642Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-07-21T06:31:05.380196+00:00.

Observation 0c4301b2-c33b-4ae7-8330-ecb8658aca76 · outbound

This paper cites The deploy- ment of ZoomIn-32B takes 4x NVIDIA A100-40G GPUs connected with PCI-E.

Locate-Then-Examine: Grounded Region Reasoning Improves Detection of AI-Generated Images The deploy- ment of ZoomIn-32B takes 4x NVIDIA A100-40G GPUs connected with PCI-E

Reference 30

Resolution: verified fuzzy; raw_fallback, observed 2026-05-18T10:16:14.835635Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-07-21T06:31:05.380196+00:00.

Pith citing papers

Observation 21894451-08cb-4ee0-aad7-8ee0006c023f · inbound

HEDGE: Heterogeneous Ensemble for Detection of AI-GEnerated Images in the Wild cites this paper.

HEDGE: Heterogeneous Ensemble for Detection of AI-GEnerated Images in the Wild Locate-Then-Examine: Grounded Region Reasoning Improves Detection of AI-Generated Images

Reference 11

Resolution: verified exact; local_arxiv, observed 2026-05-13T18:58:09.083548Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-07-21T06:31:05.380196+00:00.

Observation 31159dc6-9877-414c-9bd5-f9e6a3b7a90b · inbound

Venus-DeFakerOne: Unified Fake Image Detection & Localization cites this paper.

Venus-DeFakerOne: Unified Fake Image Detection & Localization Locate-Then-Examine: Grounded Region Reasoning Improves Detection of AI-Generated Images

Reference 37

Resolution: metadata mismatch; local_arxiv, observed 2026-05-15T05:29:46.633397Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-07-21T06:31:05.380196+00:00.

Observation 3a6eb704-1fca-4952-8c52-dacc1c720590 · inbound

XPlainVerse: A Million-Scale Benchmark for Explainable Deepfake Detection cites this paper.

XPlainVerse: A Million-Scale Benchmark for Explainable Deepfake Detection Locate-Then-Examine: Grounded Region Reasoning Improves Detection of AI-Generated Images

Reference 19

Resolution: unresolved; no resolver link, observed 2026-07-12T01:35:43.979206Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.